Ensuring the resilience of power system is the prerequisite for maintaining its normal operation after the occurrence of natural disasters. This paper proposes a data-driven transmission defense planning (DTDP) model to address the power system resilience issue against extreme weather events. DTDP enables the determination of the optimal resilience enhancement portfolio, including line hardening and construction. The target events of DTDP are selected according to survivability based severity indices. The component survivability and post-disaster system failure state are treated as random variables in two separate levels, and the selected historical data are used to construct the confidence sets of their ambiguous probability distribution. Thus, the man-made uncertainty budget can be avoided and the expected economic loss under the worst-case distribution is minimized. Moreover, a sparsification method of system failure states is designed to boost computational efficiency. The effectiveness of DTDP and its solution method are verified on a six-bus test system and RTS-79 system. The results demonstrate that the DTDP can obtain a better defense plan compared to other optimization techniques.

The offshore wind farms (OWF) are susceptible to the severe weather, which can cause the increase of component failure rate and has significant influence on the maintenance process and the reliability of wind farms. This paper proposes a sequential Markov chain Monte Carlo (MCMC) model for reliability evaluation of the OWF considering the impact of severe offshore weather. First, main factors affecting the wind turbine (WT) failure rate are analyzed. Second, a time-varying analytical model for the WT failure rate affected by wind speed and lightning is established. Three types of WT failure rates are considered: the failure rate under normal weather, that under strong wind, and that affected by lightning. Moreover, a time-varying analytical model for the repair time of main components of OWF is established by considering the influence of severe weather on offshore transportation time and maintenance efficiency after component failure. The MCMC model takes into account the temporal correlation of the weather and the repair process of failed component in the reliability evaluation. The model enables simultaneous simulation of the weather intensity and component state. For each system state generated by the MCMC model, a breadth-first search (BFS) method is applied to analyze the connectivity of the WTs and the sink node. Finally, the output of the wind farm is determined based on the wind speed data at this state. The expected energy not supply (EENS) and the generation ratio availability (GRA) indices of the OWF are evaluated to demonstrate the effectiveness of the proposed models. Further, the effects of other factors such as the enhanced protection for WT, the use of helicopter, and the weather characteristics of the OWF location on the reliability of OWF are discussed.

The highly variable nature of renewable energy has led to the concept of intra-day look-ahead unit commitment (LAUC), which aims to determine the on/off status and power outputs of generating units in a rolling-horizon fashion. LAUC is traditionally performed based on look-ahead horizon (LAH) with fixed length and resolution. Such practice can neither capture the high-risk time periods, nor achieve maximum computational efficiency. To address these issues, this article proposes a LAUC method with adaptive horizon (LAUC-AH). The method uses three parameters to describe the shape of LAH, namely length, resolution, and myopia. Taking these parameters, the forecast profile of renewable energy and load demand is aggregated using a hierarchical clustering procedure to form the LAH, which is then used to construct the LAUC optimization model. Furthermore, a deep reinforcement learning-based agent is used to dynamically adjust the parameters of LAH, such that the LAUC model can adapt to different operation statuses of the power grid. The case studies are carried out on a modified IEEE-118 test case to validate the feasibility and effectiveness of the proposed method.

This paper intends to address the dynamic repair scheduling of electric power transmission systems based on look-ahead strategy approximation. The objective is to minimize system functionality loss during the restoration stage after disruptive events. A series of decisions regarding which damaged component to be repaired has to be made successively considering currently available information of repair time and its uncertainty in the future. To achieve this goal, the dynamic repair scheduling problem is represented as a stochastic Markovian decision process (MDP). To overcome the computational complexity of MDP derived from exponentially growing state space, the cost-to-go function is approximated by a look-ahead strategy based on repair importance ordering. Stage-dependent coefficients are used to balance the approximated functionality loss at different decision stages. The tradeoff between the efficiency and optimality can be achieved by adjusting the look-ahead depth and the updating policy of look-ahead strategy. The IEEE-14 and 118-bus systems were used for performance evaluation of the proposed method and comparison with various approaches. The results show that it can produce decisions close to the best-known solutions within small amount of time.

This paper proposes a novel repair rule set (RRS) for scheduling the power system infrastructure repair after the occurrence of extreme events. RRS is made up of multiple repair rules, each of them can be applied in arbitrary post-disaster failure scenarios to rank the repair actions by priority. A learning-to-rank technique called AdaRank is used to train the repair rules by combining the weak learners derived from the dynamic repair scheduling model. Then, RRS is constructed by iteratively clustering the training cases and retraining the repair rule for each cluster. Increasing the number of repair rules within RRS allows it to differentiate various types of failure scenarios, thereby improving its performance. Further combined with multi-label K nearest neighbor (ML-KNN) technique, RRS is able to schedule the repair without the full knowledge of real-time failure information, such as the estimated repair time. The results of case studies on IEEE-118 test systems show that the proposed method has a desirable performance compared to the exact mathematical optimization model. Moreover, it reduces the requirement for failure information while significantly improving the computational efficiency.

Medium- and long-term wind power output time series are required in stochastic programming model for power system planning. Hidden Markov model (HMM) is a common method to generate wind power output time series, which can simultaneously consider the temporal and spatial correlation of multiple wind farms. However, the existing HMM methods use discrete matrix or Gaussian distribution to describe the output distribution of multiple wind farms, which usually leads to a relatively large error in statistical indices between the generated time series and the historical time series. Therefore, this paper proposes a method for generating medium- and long-term correlated output time series of multiple wind farms based on the Gaussians mixture model-Hidden Markov model (GMM-HMM). The discrete state variable in the hidden Markov model is used to describe the meteorological state. The Markov chain between discrete state variables is used to describe the temporal correlation of wind power output. The wind power output vector of multiple wind farms is used as the observation variable, and the mixed Gaussian probability distribution mapping relationship between the state variable and the multidimensional wind power output vector is established. Based on the Monte Carlo sampling method, the multi-wind farm output series satisfying the spatiotemporal correlation of historical output series are generated monthly. In the calculation example, the monthly wind power output series generated by five wind farms in Jilin Province are analyzed. The results show that the main statistical characteristics of the multi-wind power output time series generated by the proposed method are generally superior to those obtained with the traditional wind power output modeling method, which proves the superiority of the proposed method.